Cookbook - Hadoop in Action - page 167

and outputs two data sets. One has chronological information, such as issued date. The
other data set has geographical information associated with each patent. This, too, is
a map-only program, but you can apply the multiple output collectors to reducers in a
straightforward way.
Listing 7.2 Program to project different columns of input data to different files
public class MultiFile extends Configured implements Tool {
public static class MapClass extends MapReduceBase
implements Mapper<LongWritable, Text, NullWritable, Text> {
private MultipleOutputs mos;
private OutputCollector<NullWritable, Text> collector;
public void configure(JobConf conf) {
mos = new MultipleOutputs(conf);
}
public void map(LongWritable key, Text value,
OutputCollector<NullWritable, Text> output,
Reporter reporter) throws IOException {
String[] arr = value.toString().split(",", -1);
String chrono = arr[0] + "," + arr[1] + "," + arr[2];
String geo = arr[0] + "," + arr[4] + "," + arr[5];
collector = mos.getCollector("chrono", reporter);
collector.collect(NullWritable.get(), new Text(chrono));
collector = mos.getCollector("geo", reporter);
collector.collect(NullWritable.get(), new Text(geo));
}
public void close() throws IOException {
mos.close();
}
}
public int run(String[] args) throws Exception {
Configuration conf = getConf();
JobConf job = new JobConf(conf, MultiFile.class);
Path in = new Path(args[0]);
Path out = new Path(args[1]);
FileInputFormat.setInputPaths(job, in);
FileOutputFormat.setOutputPath(job, out);
job.setJobName("MultiFile");
job.setMapperClass(MapClass.class);
job.setInputFormat(TextInputFormat.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
job.setNumReduceTasks(0);
MultipleOutputs.addNamedOutput(job,
"chrono",
TextOutputFormat.class,
NullWritable.class,
Text.class);